File size: 10,058 Bytes
004975c 848b0e8 004975c 848b0e8 ede3a31 fb8a8c6 004975c 735d726 004975c 848b0e8 004975c 6153abe 004975c ee0f367 4320284 ee0f367 004975c 848b0e8 004975c b610ea9 004975c 4320284 004975c a22a3ef 004975c 848b0e8 004975c 848b0e8 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 |
import os
from flask import Flask, request, jsonify
from PIL import Image
from io import BytesIO
import torch
import base64
import io
import gradio as gr
import numpy as np
import spaces
from src.tryon_pipeline import StableDiffusionXLInpaintPipeline as TryonPipeline
from src.unet_hacked_garmnet import UNet2DConditionModel as UNet2DConditionModel_ref
from src.unet_hacked_tryon import UNet2DConditionModel
from transformers import (
CLIPImageProcessor,
CLIPVisionModelWithProjection,
CLIPTextModel,
CLIPTextModelWithProjection,
AutoTokenizer,
)
from diffusers import DDPMScheduler, AutoencoderKL
from utils_mask import get_mask_location
from torchvision import transforms
import apply_net
from preprocess.humanparsing.run_parsing import Parsing
from preprocess.openpose.run_openpose import OpenPose
from detectron2.data.detection_utils import convert_PIL_to_numpy, _apply_exif_orientation
from torchvision.transforms.functional import to_pil_image
app = Flask(__name__)
base_path = 'yisol/IDM-VTON'
example_path = os.path.join(os.path.dirname(__file__), 'example')
unet = UNet2DConditionModel.from_pretrained(
base_path,
subfolder="unet",
torch_dtype=torch.float16,
)
unet.requires_grad_(False)
tokenizer_one = AutoTokenizer.from_pretrained(
base_path,
subfolder="tokenizer",
revision=None,
use_fast=False,
)
tokenizer_two = AutoTokenizer.from_pretrained(
base_path,
subfolder="tokenizer_2",
revision=None,
use_fast=False,
)
noise_scheduler = DDPMScheduler.from_pretrained(base_path, subfolder="scheduler")
text_encoder_one = CLIPTextModel.from_pretrained(
base_path,
subfolder="text_encoder",
torch_dtype=torch.float16,
)
text_encoder_two = CLIPTextModelWithProjection.from_pretrained(
base_path,
subfolder="text_encoder_2",
torch_dtype=torch.float16,
)
image_encoder = CLIPVisionModelWithProjection.from_pretrained(
base_path,
subfolder="image_encoder",
torch_dtype=torch.float16,
)
vae = AutoencoderKL.from_pretrained(base_path,
subfolder="vae",
torch_dtype=torch.float16,
)
UNet_Encoder = UNet2DConditionModel_ref.from_pretrained(
base_path,
subfolder="unet_encoder",
torch_dtype=torch.float16,
)
parsing_model = Parsing(0)
openpose_model = OpenPose(0)
UNet_Encoder.requires_grad_(False)
image_encoder.requires_grad_(False)
vae.requires_grad_(False)
unet.requires_grad_(False)
text_encoder_one.requires_grad_(False)
text_encoder_two.requires_grad_(False)
tensor_transfrom = transforms.Compose(
[
transforms.ToTensor(),
transforms.Normalize([0.5], [0.5]),
]
)
pipe = TryonPipeline.from_pretrained(
base_path,
unet=unet,
vae=vae,
feature_extractor= CLIPImageProcessor(),
text_encoder = text_encoder_one,
text_encoder_2 = text_encoder_two,
tokenizer = tokenizer_one,
tokenizer_2 = tokenizer_two,
scheduler = noise_scheduler,
image_encoder=image_encoder,
torch_dtype=torch.float16,
)
pipe.unet_encoder = UNet_Encoder
def pil_to_binary_mask(pil_image, threshold=0):
np_image = np.array(pil_image)
grayscale_image = Image.fromarray(np_image).convert("L")
binary_mask = np.array(grayscale_image) > threshold
mask = np.zeros(binary_mask.shape, dtype=np.uint8)
for i in range(binary_mask.shape[0]):
for j in range(binary_mask.shape[1]):
if binary_mask[i, j]:
mask[i, j] = 1
mask = (mask * 255).astype(np.uint8)
output_mask = Image.fromarray(mask)
return output_mask
@spaces.GPU
def start_tryon(dict, garm_img, garment_des, is_checked, is_checked_crop, denoise_steps, seed):
device = "cuda"
openpose_model.preprocessor.body_estimation.model.to(device)
pipe.to(device)
pipe.unet_encoder.to(device)
garm_img = garm_img.convert("RGB").resize((768, 1024))
human_img_orig = dict["background"].convert("RGB")
if is_checked_crop:
width, height = human_img_orig.size
target_width = int(min(width, height * (3 / 4)))
target_height = int(min(height, width * (4 / 3)))
left = (width - target_width) / 2
top = (height - target_height) / 2
right = (width + target_width) / 2
bottom = (height + target_height) / 2
cropped_img = human_img_orig.crop((left, top, right, bottom))
crop_size = cropped_img.size
human_img = cropped_img.resize((768, 1024))
else:
human_img = human_img_orig.resize((768, 1024))
if is_checked:
keypoints = openpose_model(human_img.resize((384, 512)))
model_parse, _ = parsing_model(human_img.resize((384, 512)))
mask, mask_gray = get_mask_location('hd', "upper_body", model_parse, keypoints)
mask = mask.resize((768, 1024))
else:
mask = pil_to_binary_mask(dict['layers'][0].convert("RGB").resize((768, 1024)))
mask_gray = (1 - transforms.ToTensor()(mask)) * tensor_transfrom(human_img)
mask_gray = to_pil_image((mask_gray + 1.0) / 2.0)
human_img_arg = _apply_exif_orientation(human_img.resize((384, 512)))
human_img_arg = convert_PIL_to_numpy(human_img_arg, format="BGR")
args = apply_net.create_argument_parser().parse_args(('show', './configs/densepose_rcnn_R_50_FPN_s1x.yaml', './ckpt/densepose/model_final_162be9.pkl', 'dp_segm', '-v', '--opts', 'MODEL.DEVICE', 'cuda'))
pose_img = args.func(args, human_img_arg)
pose_img = pose_img[:, :, ::-1]
pose_img = Image.fromarray(pose_img).resize((768, 1024))
with torch.no_grad():
with torch.cuda.amp.autocast():
prompt = "model is wearing " + garment_des
negative_prompt = "monochrome, lowres, bad anatomy, worst quality, low quality"
with torch.inference_mode():
(
prompt_embeds,
negative_prompt_embeds,
pooled_prompt_embeds,
negative_pooled_prompt_embeds,
) = pipe.encode_prompt(
prompt,
num_images_per_prompt=1,
do_classifier_free_guidance=True,
negative_prompt=negative_prompt,
)
prompt = "a photo of " + garment_des
negative_prompt = "monochrome, lowres, bad anatomy, worst quality, low quality"
if not isinstance(prompt, list):
prompt = [prompt] * 1
if not isinstance(negative_prompt, list):
negative_prompt = [negative_prompt] * 1
with torch.inference_mode():
(
prompt_embeds_c,
_,
_,
_,
) = pipe.encode_prompt(
prompt,
num_images_per_prompt=1,
do_classifier_free_guidance=False,
negative_prompt=negative_prompt,
)
pose_img = tensor_transfrom(pose_img).unsqueeze(0).to(device, torch.float16)
garm_tensor = tensor_transfrom(garm_img).unsqueeze(0).to(device, torch.float16)
generator = torch.Generator(device).manual_seed(seed) if seed is not None else None
images = pipe(
prompt_embeds=prompt_embeds.to(device, torch.float16),
negative_prompt_embeds=negative_prompt_embeds.to(device, torch.float16),
pooled_prompt_embeds=pooled_prompt_embeds.to(device, torch.float16),
negative_pooled_prompt_embeds=negative_pooled_prompt_embeds.to(device, torch.float16),
num_inference_steps=denoise_steps,
generator=generator,
strength=1.0,
pose_img=pose_img.to(device, torch.float16),
text_embeds_cloth=prompt_embeds_c.to(device, torch.float16),
cloth=garm_tensor.to(device, torch.float16),
mask_image=mask,
image=human_img,
height=1024,
width=768,
ip_adapter_image=garm_img.resize((768, 1024)),
guidance_scale=2.0,
)[0]
if is_checked_crop:
out_img = images[0].resize(crop_size)
human_img_orig.paste(out_img, (int(left), int(top)))
return human_img_orig, mask_gray
else:
return images[0], mask_gray
# Fonction pour décoder une image encodée en base64 en objet PIL.Image.Image
def decode_image_from_base64(image_data):
image_data = base64.b64decode(image_data)
image = Image.open(io.BytesIO(image_data))
return image
def encode_image_to_base64(image):
buffered = BytesIO()
image.save(buffered, format="PNG")
return base64.b64encode(buffered.getvalue()).decode('utf-8')
@app.route('/tryon', methods=['POST'])
def tryon():
data = request.json
human_image = decode_image_from_base64(data['human_image'])
garment_image = decode_image_from_base64(data['garment_image'])
description = data.get('description')
use_auto_mask = data.get('use_auto_mask', True)
use_auto_crop = data.get('use_auto_crop', False)
denoise_steps = int(data.get('denoise_steps', 30))
seed = int(data.get('seed', 42))
human_dict = {
'background': human_image,
'layers': [human_image] if not use_auto_mask else None,
'composite': None
}
output_image, mask_image = start_tryon(human_dict, garment_image, description, use_auto_mask, use_auto_crop, denoise_steps, seed)
output_base64 = encode_image_to_base64(output_image)
mask_base64 = encode_image_to_base64(mask_image)
return jsonify({
'output_image': output_base64,
'mask_image': mask_base64
})
if __name__ == "__main__":
app.run(debug=True, host="0.0.0.0", port=7860)
|